Point cloud segmentation method and device, medium and electronic equipment
By screening out point cloud data of basic building structures in indoor environments and combining image processing technology, the problem of low point cloud segmentation accuracy in the existing technology is solved, and a more efficient and accurate point cloud segmentation effect is achieved.
CN119723068APending Publication Date: 2025-03-28SHANGHAI INVESTIGATION DESIGN & RES INST CO LTD
0 Cites 1 Cited by
Patent Information
- Application Number
- CN202311278588.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-28
- Publication Date
- 2025-03-28
AI Technical Summary
Technical Problem
The existing point cloud segmentation method has low segmentation accuracy when dealing with complex scenarios, especially in indoor environments, it is difficult to accurately distinguish small categories of point cloud data.
Method used
By pre-screening of point cloud data of basic building structures in the indoor environment, and combining image processing technology, images from different perspectives are acquired for segmentation processing, and finally the segmented point cloud data is obtained.
Benefits of technology
It improves the accuracy and efficiency of point cloud segmentation, enhances the processing capabilities of complex point cloud scenarios, and has a certain degree of universality and universality.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention provides a point cloud segmentation method and device, a medium and electronic equipment. Comprising the steps of obtaining initial point cloud data; the initial point cloud data is screened to obtain screened point cloud data, and the screened point cloud data does not contain point cloud data which is classified as a basic building structure in an indoor environment and is contained in the initial point cloud data; based on the screened point cloud data, a plurality of images of different view angles are obtained, and the images of different view angles are all associated with the screened point cloud data; performing segmentation processing on the images of the different visual angles to obtain segmented images of the images of the different visual angles; and obtaining segmented point cloud data based on the segmented image. The point cloud segmentation method is high in segmentation precision and can be suitable for various scenes and application fields.
Need to check novelty before this filing date? Find Prior Art